A powerful AI agent skill that naturally merges two separate photos into a single, cohesive, and visually consistent image.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install ai-image-combiner-openapi-skill
2. Manual Installation
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
3. Prompt Installation
Copy this prompt to OpenClaw to install it automatically.
Help me install ai-image-combiner-openapi-skill using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Prefer to download?
Get the raw skill files in a ZIP archive.
What is AI Image Combiner OpenAPI Skill?
The AI Image Combiner is a specialized tool designed to go beyond simple overlays. As part of the Openclaw Skills ecosystem, it leverages advanced generative AI to blend elements from two different source images, ensuring lighting, shadows, and textures are unified in the final output. This skill is ideal for creators and developers who need high-quality image synthesis without manual editing.
By integrating with the WeShop OpenAPI, this skill provides a streamlined interface for AI-driven compositing. It handles the complex work of spatial reasoning and blending, allowing users to provide custom instructions on how the two images should interact to create a professional-grade merged photo.
AI Image Combiner OpenAPI Skill Use Cases
- Creating unique marketing visuals by combining products with stylized backgrounds.
- Merging person subjects from one image into a completely different environment.
- Generating creative artistic compositions by blending two distinct photographic concepts.
- Rapid prototyping for graphic design and social media content creation.
How AI Image Combiner OpenAPI Skill Works
- Image Preparation: The agent first checks if the source images are hosted online; if local, it uses the upload endpoint to generate reusable URLs.
- Initialization: A POST request is sent to the runs endpoint specifying the ai-image-combiner agent and the target image URLs.
- Customization: Optional text descriptions guide the AI on how to handle the merge, such as specifying which elements should be dominant.
- Processing: The task enters a queue, moving through states such as Pending, Segmenting, and Running.
- Polling & Retrieval: The skill polls the execution ID until a Success status is reached, then extracts the final image URLs from the result data.
AI Image Combiner OpenAPI Skill Setup
To use this among your Openclaw Skills, you must first obtain an API key from WeShop.
# Export your API key as an environment variable
export WESHOP_API_KEY='your_api_key_here'
Ensure your development environment has HTTPS access to openapi.weshop.ai. The skill will automatically detect the WESHOP_API_KEY from your environment to authenticate requests.
AI Image Combiner OpenAPI Skill Data Schema & Taxonomy
The skill interacts with the WeShop API using a structured JSON schema for both inputs and execution tracking.
| Object | Property | Description |
|---|---|---|
| Input | images |
An array containing exactly two image URLs. |
| Params | textDescription |
Markdown-supported string for merge instructions. |
| Params | batchCount |
Integer (1-16) determining how many variations to generate. |
| Output | executions |
A list of results containing the generated image URLs and status metadata. |
AI Image Combiner OpenAPI Skill Advanced Features
- Batch Generation: Generate up to 16 different versions of a merged image in a single execution for maximum creative variety.
- Granular Logic Control: Use the
textDescriptionparameter to explicitly reference 'image 1' and 'image 2' for complex spatial arrangements. - Automated Asset Management: Built-in support for uploading local files to the WeShop CDN via the assets endpoint.
- State Polling Workflow: Robust lifecycle management with specific status tracking from Segmentation to Success.
SKILL.md
Loading
Related Openclaw Skills
SprintX OpenClaw Handoff
A specialized handoff layer that connects OpenClaw operators to SprintX via a verified proof packet workflow.
AI Image Animation Skill
An advanced AI skill that converts static images into cinematic, high-fidelity videos using the Kling generation model.
WeShop AI Lingerie Models Skill
A powerful AI skill designed to transform person photos into professional lingerie or bikini model imagery and dance videos via the WeShop OpenAPI.
PipelineGate
PipelineGate allows developers to chain Green Helix tools into sequential, multi-step execution pipelines for complex AI tasks.
AI Landscape Design Skill
An AI-powered landscape design tool that automates the transformation of outdoor spaces into various aesthetic styles using image-to-image synthesis.
Horizontal Vertical Analysis
A professional deep-research skill that reconstructs a subject's life-cycle and compares it against peers to generate original strategic insights.
Featured*
